News for hackers. Stuff that matters.
Re:Are deep neural networks dramatically overfitted? (2019) by moultano on Monday April 05, 2021 @11:04AM (#26699963)
The fact that over parametrized models can generalize better than under parameterized models, and that both are better than models that can just barely interpolate is a genuinely new insight that was not predicted by any prior theory.

There are no comments on this comment yet.